© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92658
    Prev
    Next
    INDEX
    Explanations

    questions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPAN
    -0.88
     fluxo
    -0.74
     Rheumat
    -0.73
     Rwanda
    -0.71
     bate
    -0.70
     comarca
    -0.70
     SMO
    -0.70
    Throughput
    -0.70
    没有了
    -0.69
    ילות
    -0.68
    POSITIVE LOGITS
    reject
    0.96
     reject
    0.88
     Reject
    0.88
     method
    0.87
     agents
    0.81
    Agents
    0.79
    Reject
    0.78
    json
    0.78
    qs
    0.76
     formData
    0.76
    Activations Density 0.012%

    No Known Activations